Search

Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at http://vipl.ict.ac.cn/resources/codes/code/SANet code.zip.

TGFβ pretreatment decreases NK cell cytotoxicity against o-HSV infected glioblastoma cell lines and patient-derived glioblastoma stem-like cells (S1); TGFβ mediated inhibition of NK cell and macrophages/microglia intracranial infiltration persists 2 days after oHSV infection (S2); TGFβ pretreatment decreases spleen NK cell activity in 4C8 B6D2F1 mouse model in the presence of oHSV (S3); Virus titer, macrophages/microglia infiltration levels remain similar after NK cell depletion with an asialo-GM1 antibody (S4); A single dose TGFβ treatment in the absence of oHSV is not oncogenic (S5).

Description of additional methods and procedures used in the study. Also includes Supplementary References.

Yan Guo,1,* Yue Xu,2,* Meng He,2 Xilin Chen,2 Longfei Xing,2 Tingyao Hu,2 Yi Zhang,2 Mei Du,2 Dian Zhang,2 Qian Zhang,2 Bin Li1 1Department of Acupuncture and Moxibustion, Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing Key Laboratory of Acupuncture Neuromodulation, Beijing, People’s Republic of China; 2School of Acupuncture, Moxibustion and Tuina, Beijing University of Chinese Medicine, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Bin Li, Department of Acupuncture and Moxibustion, Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing Key Laboratory of Acupuncture Neuromodulation, 23 Meishuguan Back Street, Dongcheng District, Beijing, 100010, People’s Republic of China, Tel +86-18910781852, Fax +86-87906055, Email libin@bjzhongyi.comPurpose: Knee osteoarthritis (KOA) is a chronic inflammatory disease highly associated with intra-articular hypertension, hypoxia and angiogenesis of synovial tissue. Our previous studies showed that acupotomy could treat KOA in a variety of ways, including reducing cartilage deterioration and enhancing biomechanical qualities. However, the mechanism of hypoxia and angiogenesis induced by acupotomy in KOA synovium remains unclear. This study looked for the benign intervention of acupotomy in synovial pathology.Methods: The rabbits were divided into 3 groups, Normal group, KOA group, and KOA + Acupotomy (Apo) group, with 11 rabbits in each group. The KOA rabbit model was established by the modified Videman method with six weeks. The KOA + Apo group performed the intervention. The tendon insertion of vastus medialis, vastus lateralis, rectus femoris, biceps femoris, and anserine bursa were selected as treatment points in rabbits. Rabbits were treated once every 7 days for 3 weeks. We observed the intra-articular pressure and oxygen partial pressure (BOLD MRI). The synovial morphology was monitored by Hematoxylin-Eosin Staining (HE Staining). The expression of hypoxia-inducible transcription factor-1α (HIF-1α), vascular endothelial growth factor (VEGF), interleukin-1β (IL-1β) and tumour necrosis factor-α (TNF-α) was detected using Immunohistochemical (IHC), Western Blot and Enzyme-Linked Immunosorbent Assay (ELISA).Results: Acupotomy reduced intra-articular hypertension and improved the synovial oxygen situation, synovial inflammatory and angiogenesis. HIF-1α, VEGF, IL-1β and TNF-α expression were downregulated by acupotomy.Conclusion: Acupotomy may reduce inflammation and angiogenesis in KOA rabbit by reducing abnormally elevated intra-articular pressure and improving synovial oxygen environment. The above may provide a new theoretical foundation for acupotomy treatment of KOA.Keywords: acupotomy, KOA, synovium, intra-articular pressure, hypoxia, angiogenesis

Background A significant roadblock in surgical education research has been the inability to compare trainee performance to the outcomes of those surgeons after they enter independent practice. We describe the feasibility of an innovative method to link trainee performance data with patient outcomes. Methods We extracted surgeon NPI numbers from Medicare claims data for common general surgery procedures between 2007 and 2017. Next, American Board of Surgery (ABS) trainee performance data was cross-referenced with additional resources to supplement NPI data. The patient and trainee datasets were linked using NPI number and a linkage rate was calculated. Results We identified 12,952 unique surgeons in the Medicare file. Medicare surgeons were matched with ABS records by NPI number, with 96.2% (n = 12,460) of surgeons linked successfully. Conclusions We demonstrated a novel process to link patient outcomes to trainee performance. This innovation can enable future research investigating the relationship between surgical trainee performance and patient outcomes in independent practice.

Person reidentification (reID) by convolutional neural network (CNN)-based networks has achieved favorable performance in recent years. However, most of existing CNN-based methods do not take full advantage of spatial–temporal context modeling. In fact, the global spatial–temporal context can greatly clarify local distractions to enhance the target feature representation. To comprehensively leverage the spatial–temporal context information, in this work, we present a novel block, interaction–aggregation-update (IAU), for high-performance person reID. First, the spatial–temporal IAU (STIAU) module is introduced. STIAU jointly incorporates two types of contextual interactions into a CNN framework for target feature learning. Here, the spatial interactions learn to compute the contextual dependencies between different body parts of a single frame, while the temporal interactions are used to capture the contextual dependencies between the same body parts across all frames. Furthermore, a channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts. Therefore, the IAU block enables the feature to incorporate the globally spatial, temporal, and channel context. It is lightweight, end-to-end trainable, and can be easily plugged into existing CNNs to form IAUnet. The experiments show that IAUnet performs favorably against state of the art on both image and video reID tasks and achieves compelling results on a general object categorization task. The source code is available at https://github.com/blue-blue272/ImgReID-IAnet .

Background There is a large group of deaf-mutes in the world, and sign language is their major communication tool. Therefore, it’s necessary for the deaf-mutes to communicate with hearing-speech people and the hearing-speech people also have needed to understand sign language, which produces a great demand for sign language teaching. Even though there have already been a large number of books for sign language, it is low efficient to learn sign language with books, even teaching videos. To solve this problem, we develop a smartphone-based interactive Chinese sign language teaching systemfor sign language learning. Methods The system provides a learner with some kinds of learning modes and captures the learner’s actions from its front camera of the smartphone. Right now the system provides a vocabulary set with 1000 frequently used words, and the learner can evaluate his/her sign action by subjective or objective comparison. In the mode of word recognition, the users can play any word within the vocabulary and the system will turn the top three retrieved candidates, so it can remind the learners what the sign is. Results This system provides interactive learning for a user to learn sign language high efficiently. The systemadopts an algorithm based on point cloud recognition to evaluate a user’s sign and costs about 700ms inference time for each sample, which meets the real-time requirements. Conclusion This interactive learning system decreases the communication barriers between the deaf-mutes and hearing-speechers.

In this paper, we address the semantic segmentation task with a new context aggregation scheme named object context, which focuses on enhancing the role of object information. Motivated by the fact that the category of each pixel is inherited from the object it belongs to, we define the object context for each pixel as the set of pixels that belong to the same category as the given pixel in the image. We use a binary relation matrix to represent the relationship between all pixels, where the value one indicates the two selected pixels belong to the same category and zero otherwise. We propose to use a dense relation matrix to serve as a surrogate for the binary relation matrix. The dense relation matrix is capable to emphasize the contribution of object information as the relation scores tend to be larger on the object pixels than the other pixels. Considering that the dense relation matrix estimation requires quadratic computation overhead and memory consumption w.r.t. the input size, we propose an efficient interlaced sparse self-attention scheme to model the dense relations between any two of all pixels via the combination of two sparse relation matrices. To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling (Zhao et al. 2017) and atrous spatial pyramid pooling (Chen et al. 2018). We empirically show the advantages of our approach with competitive performances on five challenging benchmarks including: Cityscapes, ADE20K, LIP, PASCAL-Context and COCO-Stuff.

State-of-the-art classification models are usually considered as black boxes since their decision processes are implicit to humans. On the contrary, human experts classify objects according to a set of explicit hierarchical criteria. For example, “ tabby is a domestic cat with stripes, dots, or lines”, where tabby is defined by combining its superordinate category ( domestic cat ) and some certain attributes (e.g., has stripes). Inspired by this mechanism, we propose an interpretable Hierarchical Criteria Network (HCN) by additionally learning such criteria. To achieve this goal, images and semantic entities (e.g., taxonomies and attributes) are embedded into a common space, where each category can be represented by the linear combination of its superordinate category and a set of learned discriminative attributes. Specifically, a two-stream convolutional neural network (CNN) is elaborately devised, which embeds images and taxonomies with the two streams respectively. The model is trained by minimizing the prediction error of hierarchy labels on both streams. Extensive experiments on two widely studied datasets (CIFAR-100 and ILSVRC) demonstrate that HCN can learn meaningful attributes as well as reasonable and interpretable classification criteria. Therefore, the proposed method enables further human feedback for model correction as an additional benefit.

Location is an important distinguishing information for instance segmentation. In this paper, we propose a novel model, called Location Sensitive Network (LSNet), for human instance segmentation. LSNet integrates instance-specific location information into one-stage segmentation framework. Specifically, in the segmentation branch, Pose Attention Module (PAM) encodes the location information into the attention regions through coordinates encoding. Based on the location information provided by PAM, the segmentation branch is able to effectively distinguish instances in feature-level. Moreover, we propose a combination operation named Keypoints Sensitive Combination (KSCom) to utilize the location information from multiple sampling points. These sampling points construct the points representation for instances via human keypoints and random points. Human keypoints provide the spatial locations and semantic information of the instances, and random points expand the receptive fields. Based on the points representation for each instance, KSCom effectively reduces the mis-classified pixels. Our method is validated by the experiments on public datasets. LSNet-5 achieves 56.2 mAP at 18.5 FPS on COCOPersons. Besides, the proposed method is significantly superior to its peers in the case of severe occlusion.

Functionality is a fundamental attribute of an object which indicates the capability to be used to perform specific actions. It is critical to empower robots the functionality knowledge in discovering appropriate objects for a task e.g. cut cake using knife. Existing research works have focused on understanding object functionality through human-object-interaction from extensively annotated image or video data and are hard to scale up. In this paper, we (1) mine object-functionality knowledge through pattern-based and model-based methods from text, (2) introduce a novel task on physical object-functionality prediction, which consumes an image and an action query to predict whether the object in the image can perform the action, and (3) propose a method to leverage the mined functionality knowledge for the new task. Our experimental results show the effectiveness of our methods.

Due to the highly complex semantic information of images, even with the same query image, the expected content-based image retrieval results could be very different and personalized in different scenarios. However, most existing hashing methods only preserve one single type of semantic similarity, making them incapable of addressing such realistic retrieval tasks. To deal with this problem, we propose a unified hashing framework to encode multiple types of information into the binary codes by exploiting convolutional networks (CNNs). Specifically, we assume that typical retrieval tasks are generally defined in two aspects, i.e. high-level semantics (e.g. object categories) and visual attributes (e.g. object shape and color). To this end, our Dual Purpose Hashing model is trained to jointly preserve two kinds of similarities characterizing the two aspects respectively. Moreover, since images with both category and attribute labels are scarce, our model is carefully designed to leverage the abundant partially labelled data as training inputs to alleviate the risk of overfitting. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the outputs of a specific CNN layer, and different retrieval tasks can be achieved by using the binary codes in different ways. Experiments on two large-scale datasets show that our method achieves comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task while being more compact than the compared methods.

Reflectional symmetry is a ubiquitous pattern in nature. Previous works usually solve this problem by voting or sampling, suffering from high computational cost and randomness. In this paper, we propose a learning-based approach to intrinsic reflectional symmetry detection. Instead of directly finding symmetric point pairs, we parametrize this self-isometry using a functional map matrix, which can be easily computed given the signs of Laplacian eigenfunctions under the symmetric mapping. Therefore, we manually label the eigenfunction signs for a variety of shapes and train a novel neural network to predict the sign of each eigenfunction under symmetry. Our network aims at learning the global property of functions and consequently converts the problem defined on the manifold to the functional domain. By disentangling the prediction of the matrix into separated bases, our method generalizes well to new shapes and is invariant under perturbation of eigenfunctions. Through extensive experiments, we demonstrate the robustness of our method in challenging cases, including different topology and incomplete shapes with holes. By avoiding random sampling, our learning-based algorithm is over 20 times faster than state-of-the-art methods, and meanwhile, is more robust, achieving higher correspondence accuracy in commonly used metrics.

We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candidate's pre-cropped face track separately and do not sufficiently consider the relationships among the candidates. This potentially limits performance, especially in challenging scenarios with low-resolution faces, multiple candidates, etc. Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties. Based on such information, our model optimizes all candidates in a unified process for robust and reliable ASD. A thorough ablation study is performed on several challenging ASD benchmarks under different settings. In particular, our method outperforms the state-of-the-art by a large margin of about 15% mean Average Precision (mAP) absolute on two challenging subsets: one with three candidate speakers, and the other with faces smaller than 64 pixels. Together, our UniCon achieves 92.0% mAP on the AVA-ActiveSpeaker validation set, surpassing 90% for the first time on this challenging dataset at the time of submission. Project website: https://unicon-asd.github.io/., Comment: 10 pages, 6 figures; to appear at ACM Multimedia 2021

If an image tells a story, the image caption is the briefest narrator. Generally, a scene graph prefers to be an omniscient generalist, while the image caption is more willing to be a specialist, which outlines the gist. Lots of previous studies have found that a scene graph is not as practical as expected unless it can reduce the trivial contents and noises. In this respect, the image caption is a good tutor. To this end, we let the scene graph borrow the ability from the image caption so that it can be a specialist on the basis of remaining all-around, resulting in the so-called Topic Scene Graph. What an image caption pays attention to is distilled and passed to the scene graph for estimating the importance of partial objects, relationships, and events. Specifically, during the caption generation, the attention about individual objects in each time step is collected, pooled, and assembled to obtain the attention about relationships, which serves as weak supervision for regularizing the estimated importance scores of relationships. In addition, as this attention distillation process provides an opportunity for combining the generation of image caption and scene graph together, we further transform the scene graph into linguistic form with rich and free-form expressions by sharing a single generation model with image caption. Experiments show that attention distillation brings significant improvements in mining important relationships without strong supervision, and the topic scene graph shows great potential in subsequent applications., Comment: published in ICCV 2021

Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes. Some existing methods attempt to establish an attribute-independent latent representation for further attribute editing. However, such attribute-independent constraint on the latent representation is excessive because it restricts the capacity of the latent representation and may result in information loss, leading to over-smooth and distorted generation. Instead of imposing constraints on the latent representation, in this work we apply an attribute classification constraint to the generated image to just guarantee the correct change of desired attributes, i.e., to "change what you want". Meanwhile, the reconstruction learning is introduced to preserve attribute-excluding details, in other words, to "only change what you want". Besides, the adversarial learning is employed for visually realistic editing. These three components cooperate with each other forming an effective framework for high quality facial attribute editing, referred as AttGAN. Furthermore, our method is also directly applicable for attribute intensity control and can be naturally extended for attribute style manipulation. Experiments on CelebA dataset show that our method outperforms the state-of-the-arts on realistic attribute editing with facial details well preserved., Submitted to IEEE Transactions on Image Processing, Code: https://github.com/LynnHo/AttGAN-Tensorflow

The explosive growth of digital images in video surveillance and social media has led to the significant need for efficient search of persons of interest in law enforcement and forensic applications. Despite tremendous progress in primary biometric traits (e.g., face and fingerprint) based person identification, a single biometric trait alone cannot meet the desired recognition accuracy in forensic scenarios. Tattoos, as one of the important soft biometric traits, have been found to be valuable for assisting in person identification. However, tattoo search in a large collection of unconstrained images remains a difficult problem, and existing tattoo search methods mainly focus on matching cropped tattoos, which is different from real application scenarios. To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning. While the features in the backbone network are shared by both tattoo detection and compact representation learning, individual latent layers of each sub-network optimize the shared features toward the detection and feature learning tasks, respectively. We resolve the small batch size issue inside the joint tattoo detection and compact representation learning network via random image stitch and preceding feature buffering. We evaluate the proposed tattoo search system using multiple public-domain tattoo benchmarks, and a gallery set with about 300K distracter tattoo images compiled from these datasets and images from the Internet. In addition, we also introduce a tattoo sketch dataset containing 300 tattoos for sketch-based tattoo search. Experimental results show that the proposed approach has superior performance in tattoo detection and tattoo search at scale compared to several state-of-the-art tattoo retrieval algorithms., Comment: Technical Report (15 pages, 14 figures)

Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many typical learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied to fulfil attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our model can leverage auxiliary data to enhance the predictive ability of attribute classifiers, which can reduce the effort of instance-level attribute annotation to some extent. By integrated into an existing deep learning framework, our model can both accurately predict attributes and learn efficient image representations. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on visual attributes and human-object interaction recognition, our method can improve the state-of-the-art performance on several widely used datasets.

In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets. While the complex image appearance variations still pose a great challenge to reliable retrieval, in light of the recent progress of Convolutional Neural Networks (CNNs) in learning robust image representation on various vision tasks, this paper proposes a novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data. Specifically, we devise a CNN architecture that takes pairs/triplets of images as training inputs and encourages the output of each image to approximate discrete values (e.g. $$+\,1$$/$$-\,1$$). To this end, the loss functions are elaborately designed to maximize the discriminability of the output space by encoding the supervised information from the input image pairs/triplets, and simultaneously imposing regularization on the real-valued outputs to approximate the desired discrete values. For image retrieval, new-coming query images can be easily encoded by forward propagating through the network and then quantizing the network outputs to binary codes representation. Extensive experiments on three large scale datasets CIFAR-10, NUS-WIDE, and SVHN show the promising performance of our method compared with the state-of-the-arts.

Expressive representations for characterizing face appearances are essential for accurate face detection. Due to different poses, scales, illumination, occlusion, etc, face appearances generally exhibit substantial variations, and the contents of each local region (facial part) vary from one face to another. Current detectors, however, particularly those based on convolutional neural networks, apply identical operations (e.g. convolution or pooling) to all local regions on each face for feature aggregation (in a generic sliding-window configuration), and take all local features as equally effective for the detection task. In such methods, not only is each local feature suboptimal due to ignoring region-wise distinctions, but also the overall face representations are semantically inconsistent. To address the issue, we design a hierarchical attention mechanism to allow adaptive exploration of local features. Given a face proposal, part-specific attention modeled as learnable Gaussian kernels is proposed to search for proper positions and scales of local regions to extract consistent and informative features of facial parts. Then face-specific attention predicted with LSTM is introduced to model relations between the local parts and adjust their contributions to the detection tasks. Such hierarchical attention leads to a part-aware face detector, which forms more expressive and semantically consistent face representations. Extensive experiments are performed on three challenging face detection datasets to demonstrate the effectiveness of our hierarchical attention and make comparisons with state-of-the-art methods.

Person re-identification (reID) plays an important role in computer vision. However, existing methods suffer from performance degradation in occluded scenes. In this work, we propose an occlusion-robust block, Region Feature Completion (RFC), for occluded reID. Different from most previous works that discard the occluded regions, RFC block can recover the semantics of occluded regions in feature space. Firstly, a Spatial RFC (SRFC) module is developed. SRFC exploits the long-range spatial contexts from non-occluded regions to predict the features of occluded regions. The unit-wise prediction task leads to an encoder/decoder architecture, where the region-encoder models the correlation between non-occluded and occluded region, and the region-decoder utilizes the spatial correlation to recover occluded region features. Secondly, we introduce Temporal RFC (TRFC) module which captures the long-term temporal contexts to refine the prediction of SRFC. RFC block is lightweight, end-to-end trainable and can be easily plugged into existing CNNs to form RFCnet. Extensive experiments are conducted on occluded and commonly holistic reID benchmarks. Our method significantly outperforms existing methods on the occlusion datasets, while remains top even superior performance on holistic datasets. The source code is available at https://github.com/blue-blue272/OccludedReID-RFCnet., 18 pages, 17 figures. The paper is accepted by TPAMI, and the code is available at https://github.com/blue-blue272/OccludedReID-RFCnet

Vision-based Continuous Sign Language Recognition (CSLR) aims to recognize unsegmented signs from image streams. Overfitting is one of the most critical problems in CSLR training, and previous works show that the iterative training scheme can partially solve this problem while also costing more training time. In this study, we revisit the iterative training scheme in recent CSLR works and realize that sufficient training of the feature extractor is critical to solving the overfitting problem. Therefore, we propose a Visual Alignment Constraint (VAC) to enhance the feature extractor with alignment supervision. Specifically, the proposed VAC comprises two auxiliary losses: one focuses on visual features only, and the other enforces prediction alignment between the feature extractor and the alignment module. Moreover, we propose two metrics to reflect overfitting by measuring the prediction inconsistency between the feature extractor and the alignment module. Experimental results on two challenging CSLR datasets show that the proposed VAC makes CSLR networks end-to-end trainable and achieves competitive performance., Accpted to ICCV 2021, code is available at: https://github.com/Blueprintf/VAC_CSLR

Teaching machines to recognize a new category based on few training samples especially only one remains challenging owing to the incomprehensive understanding of the novel category caused by the lack of data. However, human can learn new classes quickly even given few samples since human can tell what discriminative features should be focused on about each category based on both the visual and semantic prior knowledge. To better utilize those prior knowledge, we propose the SEmantic Guided Attention (SEGA) mechanism where the semantic knowledge is used to guide the visual perception in a top-down manner about what visual features should be paid attention to when distinguishing a category from the others. As a result, the embedding of the novel class even with few samples can be more discriminative. Concretely, a feature extractor is trained to embed few images of each novel class into a visual prototype with the help of transferring visual prior knowledge from base classes. Then we learn a network that maps semantic knowledge to category-specific attention vectors which will be used to perform feature selection to enhance the visual prototypes. Extensive experiments on miniImageNet, tieredImageNet, CIFAR-FS, and CUB indicate that our semantic guided attention realizes anticipated function and outperforms state-of-the-art results., Comment: 11 pages, 7 figures, 4 tables. Accepted by WACV2022

Dense video event captioning aims to generate a sequence of descriptive captions for each event in a long untrimmed video. Video-level context provides important information and facilities the model to generate consistent and less redundant captions between events. In this paper, we introduce a novel Hierarchical Context-aware Network for dense video event captioning (HCN) to capture context from various aspects. In detail, the model leverages local and global context with different mechanisms to jointly learn to generate coherent captions. The local context module performs full interaction between neighbor frames and the global context module selectively attends to previous or future events. According to our extensive experiment on both Youcook2 and Activitynet Captioning datasets, the video-level HCN model outperforms the event-level context-agnostic model by a large margin. The code is available at https://github.com/KirkGuo/HCN.

Background and aims Liver transplantation is the most effective treatment for end-stage liver disease (ESLD). Whether moderately macrosteatotic livers (30%-60%) represent a risk for worsened graft function is controversial. The uncertainty, in large part, is owing to the heterogeneous steatosis grading. Our aim was to determine the short- and long-term outcomes of moderately macrosteatotic allografts that were graded according to a standardized institutional protocol. Methods We performed a retrospective analysis of transplants performed between 1994 and 2014. All patients with allografts biopsied pretransplantation were included. Relevant donor and recipient variable were recorded. Moderately macrosteatotic livers were compared with mildly macrosteatotic and nonsteatotic livers. Primary outcomes of interest were patient survival at 90 days, 1 year, and 5 years. Cox regression analyses were carried out to compare survival between the 2 groups. Results We compared 65 allografts with moderate macrosteatosis and 810 with no or mild macrosteatosis. Patients with moderately macrosteatotic allografts were 2.69 times as likely to die within the first 90 days after transplant (75.1% vs 91.6% survival) after adjusting for donor age, donor race, recipient age, recipient race, recipient body mass index, recipient diabetes, presence of hepatocellular carcinoma, days on waitlist, Model for End-Stage Liver Disease (MELD) score at transplantation, cold ischemia time. However, for recipients who survive 90 days, moderately macrosteatotic allografts had comparable long-term survival. Conclusion Our study shows that moderate macrosteatosis is a strong predictor of early but not late mortality. Further studies are needed to distinguish the specific cohort of patients for whom moderately macrosteatotic allografts will lead to acceptable outcomes.

3D models are commonly used in computer vision and graphics. With the wider availability of mesh data, an efficient and intrinsic deep learning approach to processing 3D meshes is in great need. Unlike images, 3D meshes have irregular connectivity, requiring careful design to capture relations in the data. To utilize the topology information while staying robust under different triangulations, we propose to encode mesh connectivity using Laplacian spectral analysis, along with mesh feature aggregation blocks (MFABs) that can split the surface domain into local pooling patches and aggregate global information amongst them. We build a mesh hierarchy from fine to coarse using Laplacian spectral clustering, which is flexible under isometric transformations. Inside the MFABs there are pooling layers to collect local information and multi-layer perceptrons to compute vertex features of increasing complexity. To obtain the relationships among different clusters, we introduce a Correlation Net to compute a correlation matrix, which can aggregate the features globally by matrix multiplication with cluster features. Our network architecture is flexible enough to be used on meshes with different numbers of vertices. We conduct several experiments including shape segmentation and classification, and our method outperforms state-of-the-art algorithms for these tasks on the ShapeNet and COSEG datasets.

Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and sports teams. To overcome this difficulty, only resorting to pre-trained word embedding models is far from enough. A desired model should utilize the rich information in multiple modalities of the image to help understand the meaning of scene texts, e.g., the prominent text on a bottle is most likely to be the brand. Following this idea, we propose a novel VQA approach, Multi-Modal Graph Neural Network (MM-GNN). It first represents an image as a graph consisting of three sub-graphs, depicting visual, semantic, and numeric modalities respectively. Then, we introduce three aggregators which guide the message passing from one graph to another to utilize the contexts in various modalities, so as to refine the features of nodes. The updated nodes have better features for the downstream question answering module. Experimental evaluations show that our MM-GNN represents the scene texts better and obviously facilitates the performances on two VQA tasks that require reading scene texts., Published as a CVPR2020 paper

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due to the gap between full and weak supervisions. In this paper, we propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation. However, this constraint is lost on the CAMs trained by image-level supervision. Therefore, we propose consistency regularization on predicted CAMs from various transformed images to provide self-supervision for network learning. Moreover, we propose a pixel correlation module (PCM), which exploits context appearance information and refines the prediction of current pixel by its similar neighbors, leading to further improvement on CAMs consistency. Extensive experiments on PASCAL VOC 2012 dataset demonstrate our method outperforms state-of-the-art methods using the same level of supervision. The code is released online., To appear at CVPR 2020 (Oral)